Coding tools

Continue

Continue reads a YAML config file and lets each model declare which roles it may serve. Point it at xKiro with the standard openai provider.

Wire format

OpenAI format

Base URL

https://api.xkiro.com/v1

Configured by

~/.continue/config.yaml

Model IDs always carry the vendor prefix

Use openai/gpt-5.6-sol, not a bare gpt-5.6-sol. The current list is at GET /v1/models.

Configuration#

Continue uses YAML, and each model declares which roles it may serve. A model with no roles defaults to chat, edit, apply and summarize.

# macOS / Linux:  ~/.continue/config.yaml
# Windows:        %USERPROFILE%\.continue\config.yaml
name: xKiro
version: 1.0.0
schema: v1
models:
  - name: GPT-5.6 Sol
    provider: openai
    model: openai/gpt-5.6-sol
    apiBase: https://api.xkiro.com/v1
    apiKey: sk-xt-...
    roles:
      - chat
      - edit
      - apply

Roles decide where a model shows up

Valid roles are chat, edit, apply, autocomplete, embed, rerank and summarize. A model without autocompletewill never appear for inline completion — that is the usual reason a freshly added model "does nothing".

If it does not work#

Send one request by hand before touching Continue's settings again. A reply proves the URL and key are both fine, which means whatever is left is in the tool's own configuration — and that is a much smaller place to look.

curl https://api.xkiro.com/v1/chat/completions \
  -H "Authorization: Bearer $XKIRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-5.6-sol","messages":[{"role":"user","content":"ping"}],"max_tokens":8}'

An error naming an unknown model still counts as a success here: the request was authenticated before the model was rejected. Common failures and what each one means are on the overview page.